Intelligent Fault Diagnosis and Prognosis For Engineering Systems

The desire and need for accurate diagnostic and real predictive prognostic capabilities have been around for as long as human beings have operated complex and expensive machinery. This has been true for both mechanical and electronic systems. There has been a long history of trying to develop and implement various degrees of diagnostic and prognostic capabilities. Recently, stringent advanced diagnostic, prognostics and health management (PHM) capability requirements have begun to be placed on some of the more sophisticated new applications. A major motivation for specifying more advanced diagnostic and prognostic requirements is the realization that they are needed to fully enable and reap the benefits of new and revolutionary logistic support concepts. These logistic support concepts are called by many names and include condition-based maintenance (CBM), performance-based logistics (PBL), and autonomic logistics all of which include PHM capabilities as a key enabler.

The area of intelligent maintenance and diagnostic and prognostic–enabled CBM of machinery is a vital one for today’s complex systems in industry, aerospace vehicles, military and merchant ships, the automotive industry, and elsewhere. The industrial and military communities are concerned about critical system and component reliability and availability. The goals are both to maximize equipment up time and to minimize maintenance and operating costs. As manning levels are reduced and equipment becomes more complex, intelligent maintenance schemes must replace the old prescheduled and labor intensive planned maintenance systems to ensure that equipment continues to function. Increased demands on machinery place growing importance on keeping all equipment in service to accommodate mission-critical usage.

Course Objectives

Upon successful completion of this course, the delegates will be able to:

• Acquire knowledge and apply methods on intelligent fault diagnosis and prognosis for engineering systems
• Discuss historical perspective, system requirements, design and functional layers of fault diagnostic and prognostic systems
• Recognize the system approach to CBM/PHM that includes trade studies, FMECA, system CBM test-plan design, performance assessment, impact on maintenance and operations and control and contingency management
• Implement sensors and sensing strategies, signal processing and database management systems
• Apply fault diagnosis procedures and methods as well as fault prognosis performance metrics
• Explain logistics as the support of the system in operation

Who Should Attend?

This course is intended for all electrical, mechanical and industrial engineers.  Also beneficial for those who are dealing with computer engineering and business management.

Course Outline

Day 1
Introduction
Historical Perspective
Diagnostic and Prognostic System Requirements
Designing in Fault Diagnostic and Prognostic Systems
Diagnostic and Prognostic Functional Layers

Systems Approach to CBM/PHM
Trade Studies
Failure Modes and Effects Criticality Analysis (FMECA)
System CBM Test-Plan Design
Performance Assessment
CBM/PHM Impact on Maintenance and Operations: Case Studies
CBM/PHM in Control and Contingency Management

Day 2
Sensors and Sensing Strategies
Sensors
Sensor Placement
Wireless Sensor Networks
Smart Sensors

Signal Processing and Database Management Systems
Signal Processing in CBM/PHM
Signal Preprocessing
Signal Processing
Vibration Monitoring and Data Analysis
Real-Time Image Feature Extraction and Defect/Fault Classification
The Virtual Sensor
Fusion or Integration Technologies
Usage-Pattern Tracking
Database Management Methods

Day 3
Fault Diagnosis
The Diagnostic Framework
Historical Data Diagnostic Methods
Data-Driven Fault Classification and Decision Making
Dynamic Systems Modeling
Physical Model–Based Methods
Model-Based Reasoning
Case-Based Reasoning (CBR)
Methods for Fault Diagnosis
A Diagnostic Framework for Electrical/Electronic Systems
Case Study: Vibration-Based Fault Detection and Diagnosis for Engine Bearings

Fault Prognosis
Introduction
Model-Based Prognosis Techniques
Probability-Based Prognosis Techniques
Data-Driven Prediction Techniques
Case Studies

Day 4
Fault Diagnosis and Prognosis Performance Metrics
Introduction
CBM/PHM Requirements Definition
Feature-Evaluation Metrics
Fault Diagnosis Performance Metrics
Prognosis Performance Metrics
Diagnosis and Prognosis Effectiveness Metrics
Complexity/Cost-Benefit Analysis of CBM/PHM Systems

Day 5
Logistics: Support of the System in Operation
Product-Support Architecture, Knowledge Base, and Methods for CBM
Product Support without CBM
Product Support with CBM
Maintenance Scheduling Strategies
A Simple Example

Course Methodology

A variety of methodologies will be used during the course that includes:

• (30%) Based on Case Studies
• (30%) Techniques
• (30%) Role Play
• (10%) Concepts
• Pre-test and Post-test
• Variety of Learning Methods
• Lectures
• Case Studies and Self Questionaires
• Group Work
• Discussion
• Presentation

Course Fees

This rate includes participant’s manual, Hand-Outs, buffet lunch, coffee/tea on arrival, morning & afternoon of each day.

Course Timings

Daily Course Timings
08:00 - 08:20       Morning Coffee / Tea
08:20 - 10:00       First Session
10:00 - 10:20       Coffee / Tea / Snacks
10:20 - 12:20       Second Session
12:20 - 13:30       Lunch Break & Prayer Break
13:30 - 15:00       Last Session